Dataset Information

Computerized migraine diagnostic tools: a systematic review.

ABSTRACT:

Background

Computerized migraine diagnostic tools have been developed and validated since 1960. We conducted a systematic review to summarize and critically appraise the quality of all published studies involving computerized migraine diagnostic tools.

Methods

We performed a systematic literature search using PubMed, Web of Science, Scopus, snowballing, and citation searching. Cutoff date for search was 1 June 2021. Published articles in English that evaluated a computerized/automated migraine diagnostic tool were included. The following summarized each study: publication year, digital tool name, development basis, sample size, sensitivity, specificity, reference diagnosis, strength, and limitations. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS) tool was applied to evaluate the quality of included studies in terms of risk of bias and concern of applicability.

Results

A total of 41 studies (median sample size: 288 participants, median age = 43 years; 77% women) were included. Most (60%) tools were developed based on International Classification of Headache Disorders criteria, half were self-administered, and 82% were evaluated using face-to-face interviews as reference diagnosis. Some of the automated algorithms and machine learning programs involved case-based reasoning, deep learning, classifier ensemble, ant-colony, artificial immune, random forest, white and black box combinations, and hybrid fuzzy expert systems. The median diagnostic accuracy was concordance = 89% [interquartile range (IQR) = 76-93%; range = 45-100%], sensitivity = 87% (IQR = 80-95%; range = 14-100%), and specificity = 90% (IQR = 77-96%; range = 65-100%). Lack of random patient sampling was observed in 95% of studies. Case-control designs were avoided in all studies. Most (76%) reference tests exhibited low risk of bias and low concern of applicability. Patient flow and timing showed low risk of bias in 83%.

Conclusion

Different computerized and automated migraine diagnostic tools are available with varying accuracies. Random patient sampling, head-to-head comparison among tools, and generalizability to other headache diagnoses may improve their utility.

SUBMITTER: Woldeamanuel YW

PROVIDER: S-EPMC8793115 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:INTRODUCTION:Recanalisation therapy in acute ischaemic stroke is highly time-sensitive, and requires early identification of eligible patients to ensure better outcomes. Thus, a number of clinical assessment tools have been developed and this review examines their diagnostic capabilities. METHODS:Diagnostic performance of currently available clinical tools for identification of acute ischaemic and haemorrhagic strokes and stroke mimicking conditions was reviewed. A systematic search of the literature published in 2015-2018 was conducted using PubMed, EMBASE, Scopus and The Cochrane Library. Prehospital and in-hospital studies with a minimum sample size of 300 patients reporting diagnostic accuracy were selected. RESULTS:Twenty-five articles were included. Cortical signs (gaze deviation, aphasia and neglect) were shown to be significant indicators of large vessel occlusion (LVO). Sensitivity values for selecting subjects with LVO ranged from 23 to 99% whereas specificity was 24 to 97%. Clinical tools, such as FAST-ED, NIHSS, and RACE incorporating cortical signs as well as motor dysfunction demonstrated the best diagnostic accuracy. Tools for identification of stroke mimics showed sensitivity varying from 44 to 91%, and specificity of 27 to 98% with the best diagnostic performance demonstrated by FABS (90% sensitivity, 91% specificity). Hypertension and younger age predicted intracerebral haemorrhage whereas history of atrial fibrillation and diabetes were associated with ischaemia. There was a variation in approach used to establish the definitive diagnosis. Blinding of the index test assessment was not specified in about 50% of included studies. CONCLUSIONS:A wide range of clinical assessment tools for selecting subjects with acute stroke has been developed in recent years. Assessment of both cortical and motor function using RACE, FAST-ED and NIHSS showed the best diagnostic accuracy values for selecting subjects with LVO. There were limited data on clinical tools that can be used to differentiate between acute ischaemia and haemorrhage. Diagnostic accuracy appeared to be modest for distinguishing between acute stroke and stroke mimics with optimal diagnostic performance demonstrated by the FABS tool. Further prehospital research is required to improve the diagnostic utility of clinical assessments with possible application of a two-step clinical assessment or involvement of simple brain imaging, such as transcranial ultrasonography.

Project description:Underuse and overuse of diagnostic tests have important implications for health outcomes and costs. Decision support technology purports to optimize the use of diagnostic tests in clinical practice. The objective of this review was to assess whether computerized clinical decision support systems (CCDSSs) are effective at improving ordering of tests for diagnosis, monitoring of disease, or monitoring of treatment. The outcome of interest was effect on the diagnostic test-ordering behavior of practitioners.We conducted a decision-maker-researcher partnership systematic review. We searched MEDLINE, EMBASE, Ovid's EBM Reviews database, Inspec, and reference lists for eligible articles published up to January 2010. We included randomized controlled trials comparing the use of CCDSSs to usual practice or non-CCDSS controls in clinical care settings. Trials were eligible if at least one component of the CCDSS gave suggestions for ordering or performing a diagnostic procedure. We considered studies 'positive' if they showed a statistically significant improvement in at least 50% of test ordering outcomes.Thirty-five studies were identified, with significantly higher methodological quality in those published after the year 2000 (p = 0.002). Thirty-three trials reported evaluable data on diagnostic test ordering, and 55% (18/33) of CCDSSs improved testing behavior overall, including 83% (5/6) for diagnosis, 63% (5/8) for treatment monitoring, 35% (6/17) for disease monitoring, and 100% (3/3) for other purposes. Four of the systems explicitly attempted to reduce test ordering rates and all succeeded. Factors of particular interest to decision makers include costs, user satisfaction, and impact on workflow but were rarely investigated or reported.Some CCDSSs can modify practitioner test-ordering behavior. To better inform development and implementation efforts, studies should describe in more detail potentially important factors such as system design, user interface, local context, implementation strategy, and evaluate impact on user satisfaction and workflow, costs, and unintended consequences.